Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     unwell
    1.27
     caballo
    1.22
    ຫມ
    1.20
    нда
    1.18
    𝐭
    1.18
    Chúc
    1.15
     hermosa
    1.14
     pleasing
    1.14
    ся
    1.13
    ତ
    1.13
    POSITIVE LOGITS
    s
    1.18
     Ver
    1.10
    いる
    0.95
    CHD
    0.92
    ات
    0.92
    i
    0.89
    at
    0.83
    an
    0.81
    Ver
    0.80
     di
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.